Roundtable
A rubber duck that argues with itself
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hey HN, I'm a founder at Ovlo a supply chain company.I had a problem. After every batch of customer interviews/research/feedback sessions, I'd run ideas through an LLM to help me decide what we should build next.Except it was obvious to my cofounder I wasn't really validating anything. LLMs are incredibly good at agreeing with you in subtle ways, especially when you feed them context that already reflects your thoughts. I'd ask "Does this make sense?" and get a beautifully worded essay about why yes, obviously, this is the best thing ever.I was using AI as an echo chamber without noticing. It was like a game, you bias the model a little, it biases you a little back.So my cofounder hacked together a tiny internal tool over the weekend to break that loop. Instead of one model validating my thinking, it puts multiple personas with different expertise in the same conversation. They naturally push back on each other.It's basically a rubber duck that argues with itself.We gave it some UI and called it Roundtable: https://roundtable.ovlo.aiWould love to hear what you'all think!
HN · launched Dec 2, 2025 · 6 upvotes (top 73%) · 0 views
Niche: startup idea validation tools · 144 launches, 21 in the last 7 days ▲ +11% · Explore this niche →
Category and tags
- Horizontal
- Agent / copilot
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 144 launches in startup idea validation tools →
Could you build this?
Yes It is an LLM wrapper application that sets up multi-agent debate prompts simulating diverse personas to critique ideas.
Discussion
4 comments analyzed.
Competitors mentioned: ChatGPT, General LLMs for ideation/sanity-checking
Concerns raised: LLMs too agreeable and add positive spin even when asked to be critical, Standard LLMs not effective for honest product decision feedback
Feature requests: Add ability to use more than 2 personas in debates
Competitors
Other products that read as similar to this one : 224 launches clear the similarity bar, closest 8 shown.
Attention rank: #181 of 225 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 33 days after the earliest competitor.
- AI Roundtable · hn · 2026-03-24 · 118 upvotes · similarity 0.48
- Model-agnostic cognitive architecture for LLMs · hn · 2025-11-18 · 6 upvotes · similarity 0.44
- AI Manifesto · hn · 2026-06-24 · 5 upvotes · similarity 0.42
- an AI app that settles small couple arguments · hn · 2026-06-04 · 7 upvotes · similarity 0.42
- Mediator.ai · hn · 2026-04-20 · 160 upvotes · similarity 0.41
- Simple self-hosted LLM assistant with user-steered compounding context · hn · 2026-08-04 · 5 upvotes · similarity 0.41
- LLMs as Planners, Not Reasoners · hn · 2026-04-07 · 7 upvotes · similarity 0.40
- Copycoach AI · ph · 2026-09-20 · 1 upvotes · similarity 0.40
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.